Triple

T3608629
Position Surface form Disambiguated ID Type / Status
Subject court of Constantine the Great E76431 entity
Predicate employer P7 FINISHED
Object Crispus E37305 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Crispus | Statement: [court of Constantine the Great, employer, Crispus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Crispus
Context triple: [court of Constantine the Great, employer, Crispus]
  • A. Crispus chosen
    Crispus was the eldest son of Roman emperor Constantine the Great, a prominent Caesar and military commander who was later executed under mysterious circumstances.
  • B. Asa
    Asa is the given first name of A. Philip Randolph, the prominent American civil rights leader and labor organizer.
  • C. Asa
    Asa is a local government area in Kwara State, Nigeria, known for its predominantly rural communities and agricultural activities.
  • D. Asa
    Asa was a biblical king of Judah known for religious reforms and efforts to abolish idolatry in his kingdom.
  • E. Julian Burnside
    Julian Burnside is an Australian barrister and human rights advocate renowned for his work defending refugees and speaking out on civil liberties and social justice.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69ad85da0ba481908b3b48c69efe2b98 completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc22a3cf081908c20b6fb55be0db2 completed March 8, 2026, 6:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4330de7a08190933aa7e9dc0a65be completed March 13, 2026, 3:53 p.m.
Created at: March 8, 2026, 3:22 p.m.